TextEncodeAceStepAudio1.5 - ComfyUI Built-in Node Documentation - ComfyUI

The TextEncodeAceStepAudio1.5 node prepares text and audio-related metadata for use with the AceStepAudio 1.5 model. It takes descriptive tags, lyrics, and musical parameters, then uses a CLIP model to convert them into a conditioning format suitable for audio generation.

Inputs

Parameter	Description	Data Type	Required	Range
`clip`	The CLIP model used to tokenize and encode the input text.	CLIP	Yes	N/A
`tags`	Descriptive tags for the audio, such as genre, mood, or instruments. Supports multiline input and dynamic prompts.	STRING	Yes	N/A
`lyrics`	The lyrics for the audio track. Supports multiline input and dynamic prompts.	STRING	Yes	N/A
`seed`	A random seed value for reproducible generation. Has a control_after_generate widget. Default: 0.	INT	No	0 to 18446744073709551615
`bpm`	The beats per minute (BPM) for the generated audio. Default: 120.	INT	No	10 to 300
`duration`	The desired duration of the audio in seconds. Default: 120.0.	FLOAT	No	0.0 to 2000.0
`timesignature`	The musical time signature.	COMBO	No	`"2"` `"3"` `"4"` `"6"`
`language`	The language of the input text. Default: “en”.	COMBO	No	`"ar"` `"az"` `"bg"` `"bn"` `"ca"` `"cs"` `"da"` `"de"` `"el"` `"en"` `"es"` `"fa"` `"fi"` `"fr"` `"he"` `"hi"` `"hr"` `"ht"` `"hu"` `"id"` `"is"` `"it"` `"ja"` `"ko"` `"la"` `"lt"` `"ms"` `"ne"` `"nl"` `"no"` `"pa"` `"pl"` `"pt"` `"ro"` `"ru"` `"sa"` `"sk"` `"sr"` `"sv"` `"sw"` `"ta"` `"te"` `"th"` `"tl"` `"tr"` `"uk"` `"ur"` `"vi"` `"yue"` `"zh"` `"unknown"`
`keyscale`	The musical key and scale (major or minor).	COMBO	No	`"C major"` `"C# major"` `"Db major"` `"D major"` `"D# major"` `"Eb major"` `"E major"` `"F major"` `"F# major"` `"Gb major"` `"G major"` `"G# major"` `"Ab major"` `"A major"` `"A# major"` `"Bb major"` `"B major"` `"C minor"` `"C# minor"` `"Db minor"` `"D minor"` `"D# minor"` `"Eb minor"` `"E minor"` `"F minor"` `"F# minor"` `"Gb minor"` `"G minor"` `"G# minor"` `"Ab minor"` `"A minor"` `"A# minor"` `"Bb minor"` `"B minor"`
`generate_audio_codes`	Enable the LLM that generates audio codes. This can be slow but will increase the quality of the generated audio. Turn this off if you are giving the model an audio reference. Default: True.	BOOLEAN	No	N/A
`cfg_scale`	The classifier-free guidance scale. Higher values make the output more closely follow the prompt. Default: 2.0.	FLOAT	No	0.0 to 100.0
`temperature`	A sampling temperature. Lower values make the output more deterministic. Default: 0.85.	FLOAT	No	0.0 to 2.0
`top_p`	The nucleus sampling probability (top-p). Default: 0.9.	FLOAT	No	0.0 to 2000.0
`top_k`	The number of highest probability tokens to consider (top-k). Default: 0.	INT	No	0 to 100
`min_p`	The minimum probability threshold for token sampling (min-p). Default: 0.000.	FLOAT	No	0.0 to 1.0

Outputs

Output Name	Description	Data Type
`CONDITIONING`	The conditioning data, which contains the encoded text and audio parameters for the AceStepAudio 1.5 model.	CONDITIONING

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

Source fingerprint (SHA-256): 4bc97ec6220514b71fafde610339f2dca4ded26f68b541ed43ea492f127321f8